InfoQCraig Risi3 min readrelease notesintermediate
WSO2 Releases Agent Manager as Enterprises Look to Control Growing AI Agent Sprawl
Summary
WSO2 Agent Manager GA adds model‑agnostic identity, role‑based access, policy enforcement (40+ controls), a Kubernetes‑native sandboxed runtime, and OpenTelemetry‑based tracing/evaluation for AI agents across cloud, on‑prem and hybrid environments.
- Central inventory with verifiable agent identity, token exchange, delegation, and revocation.
- Role‑based access and 40+ built‑in policies (PII masking, rate limiting) apply to agent, MCP, and LLM layers.
- Kubernetes‑native sandbox isolates agent execution while exposing metrics via OpenTelemetry.
- Rule‑based and LLM‑based evaluation monitors token consumption, behavior drift, and response quality.
Enterprises deploying heterogeneous AI agents need a single control plane for identity, security, policy, and observability that isn’t tied to any specific model or vendor. WSO2’s platform attempts to fill that gap, offering a reusable governance layer as agent estates scale.
5/10



